mcpField
T
tooluniverse-metagenomics-analysis

tooluniverse-metagenomics-analysis

github.com/mims-harvardData & databases1.8k251 installsUpdated 2d ago
Repository

About tooluniverse-metagenomics-analysis

An analysis skill for microbiome research that combines study discovery, taxonomy, genome quality, functional annotation, and clinical associations. It emphasizes interpreting findings with literature evidence rather than merely listing taxa.

Key features

  1. 01Discover metagenomics studies
  2. 02Query GTDB taxonomy
  3. 03Assess MAG genome quality
  4. 04Annotate functions and map KEGG pathways
  5. 05Link clinical phenotypes and literature

Use cases

  1. 01Explore microbiome studies and sequencing data
  2. 02Check microbial taxonomy and naming differences
  3. 03Assess genome completeness and contamination
  4. 04Interpret links between microbes and disease phenotypes

MCP support

The skill uses ToolUniverse to retrieve information from sources including MGnify, GTDB, GMrepo, ENA, KEGG, and literature, then uses Python to process and analyze results.

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/mims-harvard/tooluniverse --skill tooluniverse-metagenomics-analysis

After installing, type/tooluniverse-metagenomics-analysisin Claude Code to confirm it loaded.

Details

From the project README

Metagenomics & Microbiome Analysis

Integrated pipeline for exploring microbiome studies, classifying taxa, assessing genome quality, linking microbial composition to clinical phenotypes, and interpreting findings through pathway analysis and literature context.

Guiding principles:

  1. Study context first -- understand biome, sequencing method, and metadata before diving into taxa
  2. Taxonomic consistency -- GTDB taxonomy as reference standard; reconcile NCBI where needed
  3. Genome quality matters -- CheckM completeness/contamination thresholds determine trustworthy MAGs
  4. Interpretation over enumeration -- explain what taxa mean for the biological question
  5. English-first queries -- use English terms in tool calls

LOOK UP, DON'T GUESS

When uncertain about any scientific fact, SEARCH databases first rather than reasoning from memory.

COMPUTE, DON'T DESCRIBE

When analysis requires computation (statistics, data processing, scoring, enrichment), write and run Python code via Bash. Don't describe what you would do — execute it and report actual results. Use ToolUniverse tools to retrieve data, then Python (pandas, scipy, statsmodels, matplotlib) to analyze it.

Core Databases

DatabaseBest For
MGnifyProcessed metagenomics studies, taxonomic/functional results
GTDBStandardized bacterial/archaeal taxonomy, species-level resolution
GMrepoGut species-to-human-health phenotype associations
ENARaw sequencing datasets and study metadata
KEGGPathway mapping for microbial functional annotations
PubMed/EuropePMCPublished microbiome-disease studies
CTDChemical-microbiome-disease relationships

Workflow

Phase 0: Parse query → organism, biome, phenotype, or accession
Phase 1: Study Discovery → MGnify_search_studies, ENAPortal_search_studies
Phase 2: Taxonomic Classification → GTDB_search_genomes, GTDB_get_species, GTDB_search_taxon
Phase 3: Genome Quality → MGnify_search_genomes, MGnify_get_genome (CheckM metrics)
Phase 4: Functional Annotation → MGnify GO terms + KEGG pathway mapping
Phase 5: Clinical Associations → GMrepo species-phenotype links
Phase 6: Literature → PubMed/EuropePMC + CTD gene-disease
Phase 7: Interpretation & Report Synthesis

Key Phase Notes

Phase 1: ENA requires structured queries (e.g., study_title="*IBD*"), not free text. If ENA fails, fall back to MGnify.

Phase 2: GTDB uses its own naming (e.g., s__Bacteroides_A fragilis vs NCBI Bacteroides fragilis). Always note discrepancies. Use GTDB_search_taxon(operation="search_taxon", query=name).

Phase 3 - Quality tiers (MIMAG):

  • High: >= 90% complete, <= 5% contamination, rRNA + >= 18 tRNAs
  • Medium: >= 50% complete, <= 10% contamination
  • Low: below medium -- flag but don't exclude

Phase 4 - Functional interpretation: Don't just list GO terms. Connect to biology:

Functional CategoryKey KEGG PathwaysSignificance
SCFA productionmap00650, map00640Gut barrier, anti-inflammatory
LPS biosynthesismap00540Pro-inflammatory, endotoxemia
Bile acid metabolismmap00120Fat absorption, FXR signaling
Tryptophan metabolismmap00380Serotonin, AhR, immune
Vitamin biosynthesismap00730/740/760Host nutritional contribution

Use kegg_search_pathway(keyword=...) (NOT query). Pathway IDs need organism prefix (hsa, ko, eco), NOT bare map.

Phase 5: GMrepo uses MeSH terms: "Crohn Disease" not "IBD", "Colitis, Ulcerative" not "UC", "Colorectal Neoplasms" not "colorectal cancer". Try NCBI taxon IDs if species name fails.

Phase 6 - Evidence grading:

  • Strong: Meta-analysis or >5 studies, consistent direction
  • Moderate: 2-5 studies consistent, or 1 large cohort
  • Preliminary: Single study or conflicting
  • Mechanistic only: In vitro/animal, no human epidemiology

Phase 7 - Report: Executive summary, study landscape, GTDB taxonomy, functional interpretation (not GO term lists), clinical relevance with evidence grades, mechanistic model, genome catalog with quality tiers, data gaps.

Edge Cases & Fallbacks

  • Taxon not in GTDB: Try partial search or fall back to MGnify (NCBI taxonomy)
  • No GMrepo data: Normal for non-gut organisms; use literature
  • GMrepo 0 results: Use formal MeSH terms or NCBI taxon IDs
  • No KEGG match: Check MetaCyc or literature

Limitations

  • GMrepo: Gut-only
  • GTDB: Bacteria/Archaea only
  • ENA: Raw data only, strict query syntax
  • No sequence analysis: Queries databases, not raw FASTQ/FASTA

Comments

Markdown supported